Multiple arm trials

This section contains the following:


A simple extension of the two-arm trial is to randomize participants to more than two groups.  For example, in a three-arm trial the intervention groups receive two different doses of a drug while the control group receives a placebo.  Such trials can be designed and conducted with relatively fewer additional resources, compared to a two-arm trial, and allow investigation of the relative effectiveness of two (or more) interventions.  These benefits can be compromised by a loss of statistical power.  For example, the sample size for a three-arm trial needs to be increased by 50% to achieve the same power as a two-arm trial.  The Trial Protocol Tool can also be used to support the development of protocols for multiple arm trials.  See Further reading for more details.

Back to top

Illustrative example - From the Annals of Surgery

A randomized multicenter three-armed trial comparing laparoscopic mesh with open preperitoneal mesh with conventional technique for inguinal hernia repair (SCUR Hernia Repair Study). (Annals of Surgery 1999; 230(2):225-231 )

Back to top

Illustrative example - From the American Journal of Surgery

A prospective randomized study comparing laparoscopic and open tension-free inguinal hernia repair with Shouldice. (The American Journal of Surgery 1998; 175:331-333)

Back to top

Further reading

Pocock SJ. Clinical Trials: A Practical Approach. Chichester: John Wiley and Sons, 1983.

Duley L and Farrell B.  Clinical Trials. London: BMJ Books, 2002.

Back to top

This page was last updated 20th May 2005.